Related papers: Beyond Interpretable Benchmarks: Contextual Learni…

Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thought to be essential for robust reasoning in AI systems,…

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…

Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in…

Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark…

In our invited talk at the AI Evaluation Workshop of the University of Bristol back in June 2022 we argued that, despite claims about successful modeling of the visual brain using ANNs, the problem is far from being solved (even for…

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Representation learning is a key element of state-of-the-art deep learning approaches. It enables to transform raw data into structured vector space embeddings. Such embeddings are able to capture the distributional semantics of their…

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock…

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning within a much broader spectrum of…

The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack…

Traditionally, the way one evaluates the performance of an Artificial Intelligence (AI) system is via a comparison to human performance in specific tasks, treating humans as a reference for high-level cognition. However, these comparisons…

A stream of conscious experience is extremely contextual; it is impacted by sensory stimuli, drives and emotions, and the web of associations that link, directly or indirectly, the subject of experience to other elements of the individual's…

The rapid advancement and widespread adoption of machine learning-driven technologies have underscored the practical and ethical need for creating interpretable artificial intelligence systems. Feature importance, a method that assigns…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and…

Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

Large language models (LLMs) are increasingly used in the social sciences to simulate human behavior, based on the assumption that they can generate realistic, human-like text. Yet this assumption remains largely untested. Existing…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning and prediction across different domains. Yet, their ability to infer temporal regularities from structured behavioral data remains underexplored. This paper…

Artificial intelligence (AI) models for computer vision trained with supervised machine learning are assumed to solve classification tasks by imitating human behavior learned from training labels. Most efforts in recent vision research…